Instructions to use di-zhang-fdu/openfugu-conductor-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use di-zhang-fdu/openfugu-conductor-3b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="di-zhang-fdu/openfugu-conductor-3b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("di-zhang-fdu/openfugu-conductor-3b")
model = AutoModelForCausalLM.from_pretrained("di-zhang-fdu/openfugu-conductor-3b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use di-zhang-fdu/openfugu-conductor-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "di-zhang-fdu/openfugu-conductor-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "di-zhang-fdu/openfugu-conductor-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/di-zhang-fdu/openfugu-conductor-3b

SGLang

How to use di-zhang-fdu/openfugu-conductor-3b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "di-zhang-fdu/openfugu-conductor-3b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "di-zhang-fdu/openfugu-conductor-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "di-zhang-fdu/openfugu-conductor-3b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "di-zhang-fdu/openfugu-conductor-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use di-zhang-fdu/openfugu-conductor-3b with Docker Model Runner:
```
docker model run hf.co/di-zhang-fdu/openfugu-conductor-3b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OpenFugu Conductor 3B

A Conductor for the OpenFugu project — an open reimplementation of Sakana AI's Fugu-Ultra orchestration line. Given a user request and a worker pool, the Conductor emits a full agentic workflow (which worker does what, in what order, seeing which prior outputs) that is then executed; the last step's output is the answer.

This checkpoint is a GRPO fine-tune of Llama-3.2-3B-Instruct on nvidia/ToolScale, using a verifiable tool-call reward (the plan's tool-call sequence is scored against the task's evaluation_criteria.actions).

Independent research artifact. Reimplements the mechanism of the Conductor paper (arXiv:2512.04388, Sakana AI); not affiliated with or derived from Sakana's proprietary product. No third-party source code was copied.

Training


Base	meta-llama/Llama-3.2-3B-Instruct
Data	nvidia/ToolScale (tool-use / orchestration tasks)
Method	GRPO (TRL), 8 generations/group, β=0 (no KL — matches the Fugu-Ultra report)
Reward	format reward (`<think>…</think><answer>[json]</answer>`) + action reward (tool-name sequence + argument match vs `evaluation_criteria.actions`)
Steps	100
Hardware	NVIDIA A800-80GB

Reward trajectory (it learns): mean reward climbed 0.70 → 1.70 over training — the format reward saturates to 1.0 within ~3 steps and the action reward rises from 0.14 to a peak of ~0.70, i.e. the model learns to emit the tool-call plan format and to match the ground-truth tool calls.

Output format

The model thinks, then emits a JSON list of tool calls:

<think> brief planning </think>
<answer>[{"name": "<tool>", "arguments": {"<arg>": "<value>"}}, ...]</answer>

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("di-zhang-fdu/openfugu-conductor-3b")
model = AutoModelForCausalLM.from_pretrained("di-zhang-fdu/openfugu-conductor-3b", torch_dtype="bfloat16")
# system+user prompt format: see train/toolscale_data.py in the OpenFugu repo

Full training/serving code, the TRINITY router line, and the architecture write-up are in the OpenFugu repository: https://github.com/trotsky1997/OpenFugu

License

Llama 3.2 Community License (this is a Llama-3.2-3B-Instruct derivative) — see https://llama.com/llama3_2/license/ . The surrounding OpenFugu code is Apache-2.0.